Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bezata/kObsidian --skill wiki-lintgit clone --depth 1 https://github.com/bezata/kObsidianWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bezata/kobsidian/wiki-lint)<a href="https://agentmods.dev/skills/bezata/kobsidian/wiki-lint"><img src="https://agentmods.dev/badge/skills/bezata/kobsidian/wiki-lint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bezata/kobsidian/wiki-lint"><img src="https://agentmods.dev/badge/skills/bezata/kobsidian/wiki-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01145 |
| Opus 5 | $0.00037 | $0.00573 |
| Sonnet 5 | $0.00015 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
wiki-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Lint
You are the wiki janitor. The user wants to know what's rotting and what to fix first. Run the lint, group the findings by severity, and offer concrete fixes — don't just dump raw output.
When to use
- User asks to "lint", "audit", "health-check", or "clean up" the wiki.
- After a run of several ingests, proactively offer to lint.
- When
wiki.querysurfaces a broken link or missing page, offer to lint the rest.
Steps
-
Call
wiki.lint. With no args for defaults; overridestaleDays(default 180) if the user wants a shorter window. The return hastotalsandfindings.{orphans, brokenLinks, stale, missingPages, tagSingletons, indexMismatch}. -
Triage. Summarize findings in roughly this priority order:
- Broken links (highest — actively misleading)
- Missing concept / entity pages (referenced but empty)
- Orphans (content that nothing links to — might be dead or unlinked)
- Index mismatch (pages missing from
index.md, orindex.mdpointing at deleted pages) - Stale sources (past
staleDays— might need refresh) - Tag singletons (tags used exactly once — often typos or one-off tags that should merge)
For each category with findings, report the count and the first 3-5 examples; offer to drill in on the rest.
-
Offer fixes. Propose concrete next actions — do NOT auto-apply without confirmation for anything that deletes or rewrites content.
- Broken links → ask user for the correct target (likely a rename
they didn't propagate); use
notes.searchto find near matches. Fix with a targetednotes.updateon the source page, or delete the link. - Missing pages → for each, use
notes.createwith the canonical frontmatter for thesuggestedKind(concept / entity / source). You can borrow the stub templates the server generates viawiki.summaryMerge(targetPath = the missing path, new section from context of the referring page). - Orphans → surface to user and ask: "link these in somewhere, or delete?" Don't delete silently.
- Index mismatch → usually fixed by a single
wiki.indexRebuild. Just run it. - Stale sources → offer to mark with a tag like
needs-refreshviatags.add, or to re-ingest if the user has an updated version. - Tag singletons → for each, suggest either merging with a close
existing tag (use
tags.listto find candidates) or removing viatags.remove. Never bulk-rename without explicit user approval — tag edits ripple.
- Broken links → ask user for the correct target (likely a rename
they didn't propagate); use
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 93 lines · 74 tokens per session scan A 42ea2ca8c5a2
wiki-lint is a skill published in the GitHub repository bezata/kObsidian (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,145 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
craft-goal
Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment's intent routes to plan.).
rag-code-review
When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. Grounds review comments in the team's actual decisions instead of generic best practices. Trigger on any review-style request — "review"…